@article{pointactvisionlanguageactionmodelswithmu,
  title = {PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction},
  author = {Shizhe Chen and Paul Pacaud and Cordelia Schmid},
  year = {2026},
  eprint = {2605.21414},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.21414},
}